© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8751
    Prev
    Next
    INDEX
    Explanations

    crochet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oko
    -0.11
    ÑĥÑĤ
    -0.10
    icals
    -0.09
    åĢı
    -0.09
    lit
    -0.09
    èĨĽ
    -0.09
    hoot
    -0.09
    åģļçĶŁæĦı
    -0.08
    lander
    -0.08
    çĶŁæĦı
    -0.08
    POSITIVE LOGITS
    çIJ¨
    0.09
    天èĬ±æĿ¿
    0.09
    inch
    0.09
    稷
    0.09
    ingleton
    0.09
    èĭĵ
    0.08
    builtin
    0.08
    ä¸įåĪ°
    0.08
    ä¸įå¼Ģ
    0.08
    çī¹æĸ¯
    0.08
    Activations Density 0.015%

    No Known Activations